Instructions to use LoRAFleet/None with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use LoRAFleet/None with LeRobot:
# See https://github.com/huggingface/lerobot?tab=readme-ov-file#installation for more details git clone https://github.com/huggingface/lerobot.git cd lerobot pip install -e .[smolvla]
# Launch finetuning on your dataset python lerobot/scripts/train.py \ --policy.path=LoRAFleet/None \ --dataset.repo_id=lerobot/svla_so101_pickplace \ --batch_size=64 \ --steps=20000 \ --output_dir=outputs/train/my_smolvla \ --job_name=my_smolvla_training \ --policy.device=cuda \ --wandb.enable=true
# Run the policy using the record function python -m lerobot.record \ --robot.type=so101_follower \ --robot.port=/dev/ttyACM0 \ # <- Use your port --robot.id=my_blue_follower_arm \ # <- Use your robot id --robot.cameras="{ front: {type: opencv, index_or_path: 8, width: 640, height: 480, fps: 30}}" \ # <- Use your cameras --dataset.single_task="Grasp a lego block and put it in the bin." \ # <- Use the same task description you used in your dataset recording --dataset.repo_id=HF_USER/dataset_name \ # <- This will be the dataset name on HF Hub --dataset.episode_time_s=50 \ --dataset.num_episodes=10 \ --policy.path=LoRAFleet/None - Notebooks
- Google Colab
- Kaggle
Download adapter_config.json from LoRAFleet/None: direct link, hf CLI and curl.
- Browser
- Download file 1.38 kB
-
https://huggingface.co/LoRAFleet/None/resolve/main/adapter_config.json
- Command line
-
hf download hf://LoRAFleet/None/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/LoRAFleet/None/resolve/main/adapter_config.json
1.38 kB
| { | |
| "alora_invocation_tokens": null, | |
| "alpha_pattern": {}, | |
| "arrow_config": null, | |
| "auto_mapping": { | |
| "base_model_class": "SmolVLAPolicy", | |
| "parent_library": "lerobot.policies.smolvla.modeling_smolvla" | |
| }, | |
| "base_model_name_or_path": "/nobackup/proj/disk/bloom/personal/shenghui/LoRAForge/third_party/CORAL/smolvla/pretrained/smolvla_libero", | |
| "bias": "none", | |
| "corda_config": null, | |
| "ensure_weight_tying": false, | |
| "eva_config": null, | |
| "exclude_modules": null, | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 32, | |
| "lora_bias": false, | |
| "lora_dropout": 0.0, | |
| "lora_ga_config": null, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": [], | |
| "monteclora_config": null, | |
| "peft_type": "LORA", | |
| "peft_version": "0.20.0", | |
| "qalora_group_size": 16, | |
| "r": 16, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": "(model\\.vlm_with_expert\\.lm_expert\\..*\\.(q|v)_proj|model\\.(state_proj|action_in_proj|action_out_proj|action_time_mlp_in|action_time_mlp_out))", | |
| "target_parameters": null, | |
| "task_type": null, | |
| "trainable_token_indices": null, | |
| "use_bdlora": null, | |
| "use_dora": false, | |
| "use_qalora": false, | |
| "use_rslora": false, | |
| "velora_config": null | |
| } |